Llm Driven Action Selection With Structured Command Parsing

via “structured action framework with llm-powered prompt engineering”

Multi-agent software company simulator — PM, architect, engineer roles collaborate on projects.

Unique: Implements a declarative action framework where each action encapsulates a prompt template, LLM invocation, and output parsing. Actions are composable and can be chained by roles, with built-in support for context injection and structured output types. This enables reusable, testable LLM operations without boilerplate.

vs others: More structured than raw LLM API calls because actions enforce consistent prompt engineering patterns, output validation, and composability. Compared to LangChain tools, MetaGPT actions are tightly integrated with the role system and message passing, enabling seamless agent coordination.